Show simple item record

dc.contributor.authorCazenave, Tristan
dc.date.accessioned2019-04-12T13:38:15Z
dc.date.available2019-04-12T13:38:15Z
dc.date.issued2018
dc.identifier.issn2475-1502
dc.identifier.urihttps://basepub.dauphine.fr/handle/123456789/18637
dc.language.isoenen
dc.subjectComputer Goen
dc.subjectdeep learningen
dc.subjectresidual networksen
dc.subject.ddc004en
dc.titleResidual Networks for Computer Goen
dc.typeArticle accepté pour publication ou publié
dc.description.abstractenDeep learning for the game of Go recently had a tremendous success with the victory of AlphaGo against Lee Sedol in March 2016. We propose to use residual networks so as to improve the training of a policy network for computer Go. Training is faster than with usual convolutional networks and residual networks achieve high accuracy on our test set and a four dan level.en
dc.relation.isversionofjnlnameIEEE Transactions on Games
dc.relation.isversionofjnlvol10en
dc.relation.isversionofjnlissue1en
dc.relation.isversionofjnldate2018-03
dc.relation.isversionofjnlpages107-110en
dc.relation.isversionofdoi10.1109/TCIAIG.2017.2681042en
dc.relation.isversionofjnlpublisherIEEE - Institute of Electrical and Electronics Engineersen
dc.subject.ddclabelInformatique généraleen
dc.relation.forthcomingnonen
dc.relation.forthcomingprintnonen
dc.description.ssrncandidatenonen
dc.description.halcandidateouien
dc.description.readershiprechercheen
dc.description.audienceInternationalen
dc.relation.Isversionofjnlpeerreviewedouien
dc.relation.Isversionofjnlpeerreviewedouien
dc.date.updated2019-03-27T15:01:15Z
hal.person.labIds989
hal.identifierhal-02098330*


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record